Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1984 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 3.0210. Min Range: -3.0210

Max Act: 2.9793. Min Act: -0.0000

Data Index: 1596296 (Python Code)

Max Activating Token Index: 503

Text #1

Max Range: 3.0210. Min Range: -3.0210

Max Act: 2.9491. Min Act: 0.0000

Data Index: 1522565 (Python Code)

Max Activating Token Index: 600

Text #2

Max Range: 3.0210. Min Range: -3.0210

Max Act: 3.0210. Min Act: -0.0000

Data Index: 1517178 (Python Code)

Max Activating Token Index: 345

Text #3

Max Range: 3.0210. Min Range: -3.0210

Max Act: 2.8353. Min Act: -0.0000

Data Index: 1597645 (Python Code)

Max Activating Token Index: 648

Text #4

Max Range: 3.0210. Min Range: -3.0210

Max Act: 2.8316. Min Act: -0.0000

Data Index: 1458393 (Python Code)

Max Activating Token Index: 216

Text #5

Max Range: 3.0210. Min Range: -3.0210

Max Act: 2.6203. Min Act: -0.0000

Data Index: 1549164 (Python Code)

Max Activating Token Index: 999

Text #6

Max Range: 3.0210. Min Range: -3.0210

Max Act: 2.5659. Min Act: -0.0000

Data Index: 1655972 (Python Code)

Max Activating Token Index: 394

Text #7

Max Range: 3.0210. Min Range: -3.0210

Max Act: 2.8251. Min Act: -0.0000

Data Index: 1412255 (Python Code)

Max Activating Token Index: 932

Text #8

Max Range: 3.0210. Min Range: -3.0210

Max Act: 2.6643. Min Act: -0.0000

Data Index: 1605224 (Python Code)

Max Activating Token Index: 26

Text #9

Max Range: 3.0210. Min Range: -3.0210

Max Act: 2.5157. Min Act: -0.0000

Data Index: 1543283 (Python Code)

Max Activating Token Index: 27

Text #10

Max Range: 3.0210. Min Range: -3.0210

Max Act: 2.4868. Min Act: -0.0000

Data Index: 1418994 (Python Code)

Max Activating Token Index: 251

Text #11

Max Range: 3.0210. Min Range: -3.0210

Max Act: 2.4565. Min Act: 0.0000

Data Index: 1648335 (Python Code)

Max Activating Token Index: 85

Text #12

Max Range: 3.0210. Min Range: -3.0210

Max Act: 2.4557. Min Act: 0.0000

Data Index: 1580564 (Python Code)

Max Activating Token Index: 715

Text #13

Max Range: 3.0210. Min Range: -3.0210

Max Act: 2.4680. Min Act: -0.0000

Data Index: 1496476 (Python Code)

Max Activating Token Index: 807

Text #14

Max Range: 3.0210. Min Range: -3.0210

Max Act: 2.4346. Min Act: -0.0000

Data Index: 1410613 (Python Code)

Max Activating Token Index: 564

Text #15

Max Range: 3.0210. Min Range: -3.0210

Max Act: 2.2890. Min Act: -0.0000

Data Index: 1404374 (Python Code)

Max Activating Token Index: 955

Text #16

Max Range: 3.0210. Min Range: -3.0210

Max Act: 2.5543. Min Act: 0.0000

Data Index: 1577744 (Python Code)

Max Activating Token Index: 847

Text #17

Max Range: 3.0210. Min Range: -3.0210

Max Act: 2.4026. Min Act: -0.0000

Data Index: 1380377 (Python Code)

Max Activating Token Index: 926

Text #18

Max Range: 3.0210. Min Range: -3.0210

Max Act: 2.5337. Min Act: -0.0000

Data Index: 1609846 (Python Code)

Max Activating Token Index: 325

Text #19

Max Range: 3.0210. Min Range: -3.0210

Max Act: 2.3789. Min Act: -0.0000

Data Index: 1638716 (Python Code)

Max Activating Token Index: 111